Multi-feature walking pedestrians detection for driving assistance systems

Abstract

Abstract-This paper deals with a pedestrian pre-crash sensor based on dense stereovision and motion analysis. We aim to provide means to deploy safety measures before a crash occurs. Depending on the concrete selected actuator, it could be interesting to know the type of object (e. g. vehicle, pedestrian, bicyclist, etc.) involved in the collision. Some actuators need the information about the collision partner type, because they have to be triggered only in specific situations, or in a situation dependent manner. We present a pedestrian detection system based on dense stereo and motion, acting as pre-crash sensor. In order to detect pedestrians, we use simple features such as object size, speed, and also more complex, motion based features. All these features are combined into a flexible, Bayesian framework.

Real Time Stereo Vision System for Safe Driving Distance Measurement-a Survey

“…Scientist and many famous car manufacturers are developing durable, accurate and real time car driver assistance systems. Many of works done by researching and developing vision system for lane tracking [13], driver monitoring [9], pedestrian or bicyclists detection [14], or car detection [15]. …”

Symmetrical Logarithm Transformation Method for Driving Vision Enhancement

“…Low visibility should be blamed in most accidents. To assist car drivers driving smoothly at night, many researches on vehicle detection using vision sensor have been conducted [1][2][3][4]. Due to probable false detection and long processing time, the achievements of these researches are impractical.…”

Research and application of variant granularity feedback recognition method based on maximal entropy and cloud-membership

“…In the feature extraction phase, with the issues of enormous dataset and multi-classes objects, it is quite difficult to represent the target completely and effectively with single feature. Therefore, the efficient and stable features through multi-feature fusion technology to represent the target in multi-direction is of great concern in various fields of pattern recognition [9][10][11][12][13][14] . Based on the discrimination degree of each feature to obtain a linear weighted feature, a tracking algorithm of moving targets with multi-feature adaptive fusion has been proposed in [12].…”